Grok Imagine 1.5 — put glass and light in motion

curl -X POST 'https://ai.im.inc/api/v1/video/generate' \
  -H "Authorization: Bearer $IMMERSIVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "image": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/inputs/0000414e-6bd9-4f21-9c5d-b0213fda27cc/input_image.png",
  "model": "grok-imagine-video-1.5",
  "prompt": "A single five-second photoreal product-material study from this image. Preserve exactly the one pink wavy glass vessel on charcoal blocks, the warm ivory table, dark wall, and direction of the white sunlight. The camera slides smoothly a few centimetres to the left, revealing real glass thickness and shifting the pink refracted caustic across the tabletop. The vessel stays firmly planted and geometrically constant, no liquid is added and no objects enter. Refined luxury still-life cinematography, tactile tiny surface imperfections, physically believable reflections and shadows, no cuts or text. Native sound is a quiet airy room tone with one very soft resonant glass tone, no speech, no vocals, no dramatic music.",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}'

# Set JOB_ID to the response's "id", then poll every few seconds until the job has finished:
curl "https://ai.im.inc/api/v1/video/$JOB_ID" \
  -H "Authorization: Bearer $IMMERSIVE_API_KEY"

# The finished response has the result at url.

const headers = { Authorization: `Bearer ${process.env.IMMERSIVE_API_KEY}` };

const response = await fetch("https://ai.im.inc/api/v1/video/generate", {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify({
    "image": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/inputs/0000414e-6bd9-4f21-9c5d-b0213fda27cc/input_image.png",
    "model": "grok-imagine-video-1.5",
    "prompt": "A single five-second photoreal product-material study from this image. Preserve exactly the one pink wavy glass vessel on charcoal blocks, the warm ivory table, dark wall, and direction of the white sunlight. The camera slides smoothly a few centimetres to the left, revealing real glass thickness and shifting the pink refracted caustic across the tabletop. The vessel stays firmly planted and geometrically constant, no liquid is added and no objects enter. Refined luxury still-life cinematography, tactile tiny surface imperfections, physically believable reflections and shadows, no cuts or text. Native sound is a quiet airy room tone with one very soft resonant glass tone, no speech, no vocals, no dramatic music.",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }),
});
const job = await response.json();

// Poll every few seconds while the job is still running.
const running = ["pending", "queued", "submitted", "starting", "processing", "running", "streaming", "in_queue", "in_progress"];
let result;
do {
  await new Promise((resolve) => setTimeout(resolve, 5000));
  result = await (await fetch(`https://ai.im.inc/api/v1/video/${job.id}`, { headers })).json();
} while (running.includes(String(result.status).toLowerCase()));

console.log(result.url);

import os
import time

import requests

headers = {"Authorization": f"Bearer {os.environ['IMMERSIVE_API_KEY']}"}

job = requests.post(
    "https://ai.im.inc/api/v1/video/generate",
    headers=headers,
    json={
        "image": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/inputs/0000414e-6bd9-4f21-9c5d-b0213fda27cc/input_image.png",
        "model": "grok-imagine-video-1.5",
        "prompt": "A single five-second photoreal product-material study from this image. Preserve exactly the one pink wavy glass vessel on charcoal blocks, the warm ivory table, dark wall, and direction of the white sunlight. The camera slides smoothly a few centimetres to the left, revealing real glass thickness and shifting the pink refracted caustic across the tabletop. The vessel stays firmly planted and geometrically constant, no liquid is added and no objects enter. Refined luxury still-life cinematography, tactile tiny surface imperfections, physically believable reflections and shadows, no cuts or text. Native sound is a quiet airy room tone with one very soft resonant glass tone, no speech, no vocals, no dramatic music.",
        "duration": 5,
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "generate_audio": True,
    },
    timeout=300,
).json()

# Poll every few seconds while the job is still running.
running = {"pending", "queued", "submitted", "starting", "processing", "running", "streaming", "in_queue", "in_progress"}
while True:
    time.sleep(5)
    result = requests.get(f"https://ai.im.inc/api/v1/video/{job['id']}", headers=headers, timeout=60).json()
    if str(result.get("status", "")).lower() not in running:
        break

print(result["url"])

{
    "id": "d4fbfda3e191888cab830fa84e8f0014",
    "url": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/outputs/0000414e-6bd9-4f21-9c5d-b0213fda27cc/result.mp4",
    "status": "succeeded",
    "duration": "5.00",
    "model_name": "grok-imagine-video-1.5"
}

Your browser blocked the clipboard. Select the text and copy it by hand.